Dannecker Energy Time Series Forecasting

Efficient and Accurate Forecasting of Evolving Time Series from the Energy Domain
1. Auflage 2015
ISBN: 978-3-658-11039-0
Verlag: Springer
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 241 Seiten

Lars Dannecker developed a novel online forecasting process that significantly improves how forecasts are calculated. It increases forecasting efficiency and accuracy, as well as allowing the process to adapt to different situations and applications. Improving the forecasting efficiency is a key pre-requisite for ensuring stable electricity grids in the face of an increasing amount of renewable energy sources. It is also important to facilitate the move from static day ahead electricity trading towards more dynamic real-time marketplaces. The online forecasting process is realized by a number of approaches on the logical as well as on the physical layer that we introduce in the course of this book.Nominated for the Georg-Helm-Preis 2015 awarded by the Technische Universität Dresden.

Lars Dannecker holds a diploma in media computer science from the Technische Universität Dresden and is pursuing a doctorate as a member of the Database Technology Group led by Prof. Dr.-Ing. Wolfgang Lehner. 

Autoren/Hrsg.

Dannecker, Lars

Inhaltsverzeichnis

1;Preface;6
2;Acknowledgements;8
3;Contents;10
4;List of Figures;13
5;List of Tables;16
6;Chapter 1 Introduction;17
7;Chapter 2 The European Electricity Market: A Market Study;26
7.1;2.1 Current Developments in the European Electricity Market;27
7.1.1;2.1.1 Structure of the European Electricity Market;27
7.1.2;2.1.2 Development of Renewable Energy Sources in Europe and Germany;28
7.1.3;2.1.3 Impact of Volatile Renewable Energy Sources;32
7.1.4;2.1.4 How to Keep the Electricity Grid in Balance;35
7.1.5;2.1.5 Extending the Transmission Grid and Energy Storage;40
7.1.6;2.1.6 Demand-Side Management and Demand-Response;45
7.1.7;2.1.7 Changes on the European Electricity Market;47
7.1.8;2.1.8 Improvements in Forecasting Energy Demand and Renewable Supply;52
7.2;2.2 The MIRABEL Project: Exploiting Demand and Supply Side Flexibility;56
7.2.1;2.2.1 Flex-Offers;56
7.2.2;2.2.2 Architecture of MIRABEL’s EDMS;58
7.2.3;2.2.3 Basic and Advanced Use-Case;60
7.3;2.3 Conclusion;61
8;Chapter 3 The Current State of Energy Data Management and Forecasting;63
8.1;3.1 Data Characteristics in the Energy Domain;64
8.1.1;3.1.1 Seasonal Patterns;65
8.1.2;3.1.2 Aggregation-Level-Dependent Predictability;67
8.1.3;3.1.3 Time Series Context and Context Drifts;70
8.1.4;3.1.4 Typical Data Characteristics of Energy Time Series;72
8.2;3.2 Forecasting in the Energy Domain;73
8.2.1;3.2.1 Forecast Models with Autoregressive Structures;73
8.2.2;3.2.2 Exponential Smoothing;77
8.2.3;3.2.3 Machine Learning Techniques;80
8.3;3.3 Forecast Models Tailor-Made for the Energy Domain;82
8.3.1;3.3.1 Exponential Smoothing for the Energy Domain;83
8.3.2;3.3.2 A multi-equation forecast model using autoregression;84
8.4;3.4 Estimation of Forecast Models;86
8.4.1;3.4.1 Optimization of Derivable Functions;87
8.4.2;3.4.2 Optimization of Arbitrary Functions;88
8.4.3;3.4.3 Incremental Maintenance;90
8.4.4;3.4.4 Local and Global Forecasting Algorithms Used in this book;91
8.5;3.5 Challenges for Forecasting in the Energy Domain;96
8.5.1;3.5.1 Exponentially Increasing Search Space;96
8.5.2;3.5.2 Multi-Optima Search Space;97
8.5.3;3.5.3 Continuous Evaluation and Estimation;98
8.5.4;3.5.4 Further Challenges;99
9;Chapter 4 The Online Forecasting Process: Efficiently Providing Accurate Predictions;100
9.1;4.1 Requirements for Designing a Novel Forecasting Process;100
9.2;4.2 The Current Forecasting Calculation Process;102
9.3;4.3 The Online Forecasting Process;107
9.3.1;4.3.1 The Forecast Model Repository;109
9.3.2;4.3.2 A Flexible and Iterative Optimization for Forecast Models;112
9.3.3;4.3.3 Evaluation;121
9.4;4.4 Designing a Forecasting System for the New Electricity Market;126
9.4.1;4.4.1 Integrating Forecasting into Data Management Systems;127
9.4.2;4.4.2 Creating a Common Architecture for EDMSs;128
9.4.3;4.4.3 Architecture of an Integrated Forecasting Component;130
10;Chapter 5 Optimizations on the Logical Layer: Context-Aware Forecasting;133
10.1;5.1 Context-Aware Forecast Model Materialization;134
10.1.1;5.1.1 Case-based Reasoning and Context-Awareness in General;134
10.1.2;5.1.2 The Context-Aware Forecast Model Repository;136
10.1.3;5.1.3 Decision Criteria;137
10.1.4;5.1.4 Preserving Forecast Models Using Time Series Context;139
10.1.5;5.1.5 Forecast Model Retrieval and Assessment;144
10.1.6;5.1.6 Evaluation;149
10.2;5.2 A Framework for Efficiently Integrating External Information;153
10.2.1;5.2.1 Separating the Forecast Model;154
10.2.2;5.2.2 Reducing the Dimensionality of the External Information Model;155
10.2.3;5.2.3 Determining the Final External Model;158
10.2.4;5.2.4 Creating a Combined Forecast Model;160
10.2.5;5.2.5 Integration with the Online Forecasting Process;161
10.2.6;5.2.6 Experimental Evaluation;163
10.3;5.3 Exploiting Hierarchical Time Series Structures;168
10.3.1;5.3.1 Forecasting in Hierarchies;169
10.3.2;5.3.2 Approach Outline;170
10.3.3;5.3.3 Classification of Forecast Model Coefficients and Parameters;171
10.3.4;5.3.4 Aggregation in Detail;173
10.3.5;5.3.5 Applying the System to Real-World Forecast Models;176
10.3.6;5.3.6 Hierarchical Communication;178
10.3.7;5.3.7 Experimental Evaluation;179
10.4;5.4 Conclusion;184
11;Chapter 6 Optimizations on the Physical Layer: A Forecast-Model-Aware Time Series Storage;186
11.1;6.1 Related Work;187
11.1.1;6.1.1 Optimizing Time Series Management;187
11.1.2;6.1.2 Special Purpose DMS;188
11.1.3;6.1.3 Summarizing comparison;190
11.2;6.2 Creating an Access-Pattern-Aware Time Series Storage;191
11.2.1;6.2.1 Model Access Patterns;192
11.2.2;6.2.2 Access-Pattern-Aware Storage;195
11.3;6.3 Applying the Access-Pattern-Aware Storage to Real-World Forecast Models;200
11.3.1;6.3.1 Optimized Storage for Single-Equation Models;200
11.3.2;6.3.2 Optimized Storage for Multi-Equation Models;203
11.4;6.4 Evaluation;206
11.4.1;6.4.1 Single-Equation Models;207
11.4.2;6.4.2 Multi-Equation Models;209
11.5;6.5 Conclusion;214
12;Chapter 7 Conclusion and Future Work;216
13;References;221